TheArtist-MusicTransformer-ft-pop80-v2

TheArtist Music Transformer — F1 v2 (Pop 10K Mix, selection-corrected retrain)

Selection-corrected retrain of the F1 slot: the Phase-0 pop baseline fine-tuned on jazz with a 10,000-sequence pop rehearsal buffer, identical in recipe to ft-pop80 except that the best checkpoint is selected on a jazz-only validation subset (select_best_on: jazz_val) instead of the pop-dominated validation mix. Held-out jazz top-1 reaches 80.31 (+7.45 pp over the un-adapted state) at a −0.48 pp pop cost. One of the models from the paper How Far Can Chord-Symbol Time-Series Adaptation Carry Genre Identity? (Lee, 2026).

Recommended for chord-composition workflows targeting pop/rock with genuine jazz coloration — jazz substitutions (secondary dominants, ii–V detours) appear selectively over a pop harmonic root. Choose ft-pop29 (F4) when jazz is the primary target.

Paper · Code · Demo · All models

Accepted at ISMIR 2026 as a Late-Breaking Demo: Where Does Genre Stop Following the Chords? A Fixed-Frame Listening Probe of Bounded Chord-Symbol Genre Identity (TheArtist)

Why a v2 exists. The v1 release (ft-pop80) shipped best.pt weights that coincide with the Phase-0 pop baseline — a checkpoint-selection artifact explained in the note on that card. This retrain changes only the selection metric; its best.pt is verified hash-distinct from Phase-0 (full-state SHA-256 b47144d4db058638… vs 3875f40784f19811…) and embodies the jazz-leaning adaptation the F1 slot was designed for. The 11 per-genre lora-* adapters were trained on the v1 released base and remain paired with it, not with this checkpoint — use this repo as a standalone jazz-leaning base.

Model details

Usage

Requires torch, huggingface_hub. The repo bundles model.py and tokenizer.py, so nothing needs to be cloned from GitHub.

import sys
import torch
from huggingface_hub import snapshot_download

# Download the full repo (model.py, tokenizer.py, best.pt, config.json).
ckpt_dir = snapshot_download(repo_id="PearlLeeStudio/TheArtist-MusicTransformer-ft-pop80-v2")
sys.path.insert(0, ckpt_dir)  # so the next two imports resolve

from model import MusicTransformer
from tokenizer import ChordTokenizer

tokenizer = ChordTokenizer()
ckpt = torch.load(f"{ckpt_dir}/best.pt", map_location="cpu", weights_only=False)
model = MusicTransformer(
    vocab_size=tokenizer.vocab_size,
    d_model=512, n_heads=8, d_ff=2048, n_layers=8,
    max_seq_len=256, dropout=0.0, pad_id=tokenizer.pad_id,
)
model.load_state_dict(ckpt["model_state_dict"])
model.eval()

# Prompt = ii-V-I in C major; ask for a jazz-flavoured continuation.
song = {
    "key": "Cmaj", "time_signature": "4/4", "genre": "jazz",
    "bars": [["Dm7", "G7"], ["Cmaj7"]],
}
prompt_ids = tokenizer.encode_sequence(song)[:-1]
ids = torch.tensor([prompt_ids])
with torch.no_grad():
    for _ in range(32):
        logits = model(ids)
        next_id = torch.multinomial(
            torch.softmax(logits[:, -1, :] / 0.8, dim=-1), 1,
        )
        ids = torch.cat([ids, next_id], dim=-1)
        if next_id.item() == tokenizer.eos_id:
            break
print(tokenizer.decode(ids[0].tolist()))

Evaluation

Teacher-forced metrics on the held-out per-genre test sets, best epoch 6:

The headline jazz numbers are measured on the 6-source jazz test (167 sequences); on the unified 9-source jazz test (501 sequences) the same weights score 75.05, so figures across the two test sets are not cell-comparable. For this run (seed 42, 6-source corpus) the mixed validation loss rose monotonically (0.5578 → 0.5929) — min-mixed-val selection would have retained the un-adapted epoch 3, while jazz-only selection picks epoch 6. In matched-data multi-seed retrains on the 9-source corpus (seeds 42, 123, 7), jazz-val selection reliably yields an adapted base: jazz top-1 75.76 ± 0.03, all hash-distinct from Phase-0. The full per-epoch training curve, including the jazz_val_* selection-metric columns, ships in this repo's eval_results.csv.

<!-- real-song-eval:begin -->

Per-genre real-song eval

Paired against Phase-0 on the same songs, this checkpoint gains +5.17 pp mean jazz top-1 (median +5.19, 6/10 songs win) at −0.42 pp pop, with all other genres within ±1.1 pp. For the eight genres without a [GENRE:X] token in the 351-token vocabulary (all beyond pop/jazz except rock, blues, and bossa) the model runs without a genre tag — the per-genre lora-* adapters, paired with the v1 base, are the recommended path there. 130 songs (10 per genre × 13 genres, seed 42) drawn from held-out val/test partitions — pop from McGill Billboard (CC0), jazz from public standards corpora, classical from Bach chorales, the other ten genres from the matching Chordonomicon subsets (CC BY-NC 4.0; titles are Spotify track IDs by upstream policy).

<!-- real-song-eval:end -->

Training data

All 1,513 jazz training sequences (Jazz Harmony Treebank, JazzStandards, Weimar Jazz Database, JAAH) plus 10,000 pop rehearsal sequences sub-sampled with seed 42 from the Phase-0 pop training split — the same mix as v1, drawn from the rebuilt 6-source splits.

Fine-tune hyperparameters as configured: peak learning rate 2 × 10⁻⁵, two-epoch warmup, ten epochs maximum with patience 5, identical to v1; only select_best_on: jazz_val differs. As applied (verified 2026-09-02 from the saved optimizer and scheduler state): the run resumed from the Phase-0 checkpoint with that state restored, so the configured warmup never fired, epoch 3 ran at the inherited learning rate 0 (which is why epoch_0003.pt is bit-identical to Phase-0), and epochs 4 to 9 followed the tail of the Phase-0 cosine on base 3 × 10⁻⁴ (2.56 × 10⁻⁴ down to 1.14 × 10⁻⁵), as the per-epoch lr column of the training log records.

License

CC BY-NC 4.0 (weights; matching Chordonomicon, the dominant training corpus). Research, paper replication, portfolio, and demo use are permitted; commercial use is not.

Citation

@misc{lee2026chordmix,
  title         = {Empirical Study of Pop and Jazz Mix Ratios for Genre-Adaptive Chord Generation},
  author        = {Lee, Jinju},
  year          = {2026},
  eprint        = {2605.04998},
  archivePrefix = {arXiv}
}

@misc{lee2026chordtimeseries,
  title         = {How Far Can Chord-Symbol Time-Series Adaptation Carry Genre Identity?},
  author        = {Lee, Jinju},
  year          = {2026},
  eprint        = {2606.07334},
  archivePrefix = {arXiv}
}